BetterDB-inc/monitor

vagent-cache-py-v0.7.0 scope: agent-cache-py Breaking

This release includes 2 breaking changes for platform teams planning a safe upgrade.

Published 1mo Monitoring & Metrics

View tool

✓ No known CVEs patched

Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

prometheus monitoring obsevability redis valkey

Affected surfaces

breaking_upgrade

ReleasePort's take

Light signal

editorial:auto 1mo

The LlamaIndex adapter now incorporates tool definitions into cache keys when `tools` is provided to `prepare_params()`. Existing cached entries will become invalid after the upgrade.

Why it matters: Cache key computation changes break existing caches; operators must invalidate or rebuild them post‑upgrade. Severity rated high (70) indicating significant impact.

Summary

AI summary

LlamaIndex adapter now includes tools in cache keys and supports a tools argument in prepare_params().

Changes in this release

Type	Severity	Summary	CVE
Breaking	High	Cache keys changed for tool-using requests on the LlamaIndex adapter; existing cached entries will miss once after upgrade. Cache keys changed for tool-using requests on the LlamaIndex adapter; existing cached entries will miss once after upgrade. Source: llm_adapter@2026-06-11 Confidence: high	—
Feature	Low	'prepare_params()' now accepts a `tools` keyword argument (and `LlamaIndexPrepareOptions.tools`). 'prepare_params()' now accepts a `tools` keyword argument (and `LlamaIndexPrepareOptions.tools`). Source: llm_adapter@2026-06-11 Confidence: high	—
Bugfix	Medium	LlamaIndex adapter: tool definitions now included in cache key when `tools` is passed to `prepare_params()`. LlamaIndex adapter: tool definitions now included in cache key when `tools` is passed to `prepare_params()`. Source: llm_adapter@2026-06-11 Confidence: high	—

Full changelog

Fixed

LlamaIndex adapter: tool definitions now included in cache key when tools is passed to prepare_params(). Only serializable metadata is used; callable closures are never serialized.

Changed

Cache keys changed for tool-using requests on the LlamaIndex adapter. Existing cached entries for those requests will be a one-time miss after upgrade — intended, as the prior entries were not safe to reuse across differing tool sets.
prepare_params() now accepts a tools keyword argument (and LlamaIndexPrepareOptions.tools). Omitting it falls back to messages-only keying (prior behavior).

Known limitations

LangChain adapter: tool-schema drift is not reflected in the cache key — the framework's BaseCache interface only exposes (prompt, llm_string). Documented limitation, unchanged.

Full Changelog: https://github.com/BetterDB-inc/monitor/compare/agent-cache-py-v0.6.1...agent-cache-py-v0.7.0

Breaking Changes

Cache keys for tool-using requests on the LlamaIndex adapter have changed; existing entries will be invalidated once after upgrade.
`prepare_params()` now requires a `tools` keyword argument (or `LlamaIndexPrepareOptions.tools`) to include tools in cache key calculation.

View diff on GitHub

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Share on X Share on Bluesky

Track BetterDB-inc/monitor

Get notified when new releases ship.

About BetterDB-inc/monitor

Valkey-first observability with Redis compatibility. Query real-time metrics, analyze slow commands, detect hot keys, and investigate performance issues directly from AI coding assistants.

All releases →

Related context

Related tools

Earlier breaking changes

vagent-cache-v0.7.0 Cache keys for tool-using requests changed on Vercel and LlamaIndex adapters; existing entries become one-time misses.
vagent-v1.5.0 TLS is now mandatory; agent exits with error if `--valkey-tls true` is not set for IAM auth mode.